kelseye commited on
Commit
76acc61
·
verified ·
1 Parent(s): 9355758

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -3,7 +3,7 @@ license: apache-2.0
3
  ---
4
  # Templates-Inpainting (FLUX.2-klein-base-4B)
5
 
6
- This model is one of the open-source Diffusion Templates series models from [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio). Specifically designed for inpainting, it accepts an original image and a mask image, then generates new content within the masked region based on natural language prompts, seamlessly blending with the surrounding unmasked background.
7
 
8
  ## Results
9
 
@@ -141,12 +141,12 @@ image = template(
141
  pipe,
142
  prompt="An orange cat is sitting on a stone.",
143
  seed=0, cfg_scale=4, num_inference_steps=50,
144
- template_inputs = [{
145
  "image": Image.open("data/examples/templates/image_reference.jpg"),
146
  "mask": Image.open("data/examples/templates/image_mask_1.jpg"),
147
  "force_inpaint": True,
148
  }],
149
- negative_template_inputs = [{
150
  "image": Image.open("data/examples/templates/image_reference.jpg"),
151
  "mask": Image.open("data/examples/templates/image_mask_1.jpg"),
152
  }],
@@ -156,11 +156,11 @@ image = template(
156
  pipe,
157
  prompt="A cat wearing sunglasses is sitting on a stone.",
158
  seed=0, cfg_scale=4, num_inference_steps=50,
159
- template_inputs = [{
160
  "image": Image.open("data/examples/templates/image_reference.jpg"),
161
  "mask": Image.open("data/examples/templates/image_mask_2.jpg"),
162
  }],
163
- negative_template_inputs = [{
164
  "image": Image.open("data/examples/templates/image_reference.jpg"),
165
  "mask": Image.open("data/examples/templates/image_mask_2.jpg"),
166
  }],
 
3
  ---
4
  # Templates-Inpainting (FLUX.2-klein-base-4B)
5
 
6
+ This model is one of the open-source Diffusion Templates series models from [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio). Specifically designed for inpainting tasks, it accepts an original image and a mask image, then generates new content within the masked region based on natural language prompts, seamlessly blending with the surrounding unmasked background.
7
 
8
  ## Results
9
 
 
141
  pipe,
142
  prompt="An orange cat is sitting on a stone.",
143
  seed=0, cfg_scale=4, num_inference_steps=50,
144
+ template_inputs=[{
145
  "image": Image.open("data/examples/templates/image_reference.jpg"),
146
  "mask": Image.open("data/examples/templates/image_mask_1.jpg"),
147
  "force_inpaint": True,
148
  }],
149
+ negative_template_inputs=[{
150
  "image": Image.open("data/examples/templates/image_reference.jpg"),
151
  "mask": Image.open("data/examples/templates/image_mask_1.jpg"),
152
  }],
 
156
  pipe,
157
  prompt="A cat wearing sunglasses is sitting on a stone.",
158
  seed=0, cfg_scale=4, num_inference_steps=50,
159
+ template_inputs=[{
160
  "image": Image.open("data/examples/templates/image_reference.jpg"),
161
  "mask": Image.open("data/examples/templates/image_mask_2.jpg"),
162
  }],
163
+ negative_template_inputs=[{
164
  "image": Image.open("data/examples/templates/image_reference.jpg"),
165
  "mask": Image.open("data/examples/templates/image_mask_2.jpg"),
166
  }],